CN117370767B - User information evaluation method and system based on big data - Google Patents
User information evaluation method and system based on big data Download PDFInfo
- Publication number
- CN117370767B CN117370767B CN202311672376.2A CN202311672376A CN117370767B CN 117370767 B CN117370767 B CN 117370767B CN 202311672376 A CN202311672376 A CN 202311672376A CN 117370767 B CN117370767 B CN 117370767B
- Authority
- CN
- China
- Prior art keywords
- interaction
- range
- analysis result
- information
- user interaction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 21
- 230000003993 interaction Effects 0.000 claims abstract description 293
- 238000004458 analytical method Methods 0.000 claims abstract description 129
- 230000028161 membrane depolarization Effects 0.000 claims abstract description 126
- 230000002159 abnormal effect Effects 0.000 claims abstract description 90
- 238000000034 method Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 20
- 238000000611 regression analysis Methods 0.000 claims description 17
- 230000007704 transition Effects 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 7
- 230000001502 supplementing effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 238000003491 array Methods 0.000 description 2
- 238000001212 derivatisation Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011234 economic evaluation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
Abstract
According to the big data-based user information evaluation method and system, user interaction information to be evaluated is obtained, and a first interaction abnormal range in the user interaction information is determined; obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction anomaly range; splicing the depolarization analysis results of the first interaction abnormal range according to the first depolarization analysis results to obtain a spliced second interaction abnormal range; and loading the second interaction abnormal range to the user interaction information to obtain the evaluated target user interaction information. Therefore, the first interaction abnormal range is spliced by extracting the first depolarization analysis result of the constraint range surrounding the first interaction abnormal range, and the spliced second interaction abnormal range is loaded to the user interaction information, so that the user information can be accurately evaluated, key description content of the user interaction information can be effectively obtained, and better assistance is provided for subsequent services.
Description
Technical Field
The application relates to the technical field of data evaluation, in particular to a user information evaluation method and system based on big data.
Background
The information evaluation method is an information analysis method. The method is a process for forming supporting information capable of meeting decision requirements through optimization selection and comparison evaluation on the basis of analyzing and synthesizing a large amount of related information, and generally comprises the forms of comprehensive evaluation, technical and economic evaluation, strength level comparison, function evaluation, result evaluation, scheme selection and the like.
At present, the information acquired by enterprises is not uniform, so that the interaction between the enterprises and related policy information is not smooth, and the enterprises are difficult to transact. The enterprise does not know whether the business policy is suitable for the enterprise, so that related matters cannot be accurately and rapidly transacted. Therefore, a technical solution is needed to improve the above technical problems.
Disclosure of Invention
In order to improve the technical problems in the related art, the application provides a user information evaluation method and system based on big data.
In a first aspect, a method for evaluating user information based on big data is provided, the method comprising: obtaining user interaction information to be evaluated, and determining a first interaction abnormal range in the user interaction information; obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction anomaly range; splicing the depolarization analysis results of the first interaction abnormal range by combining the first depolarization analysis results to obtain a spliced second interaction abnormal range; and loading the second interaction abnormal range to the user interaction information to obtain the evaluated target user interaction information.
In an independently implemented embodiment, the obtaining the first depolarization analysis result corresponding to the constraint range surrounding the first interaction anomaly range includes: performing derivative treatment on the first interaction abnormal range to obtain a target interaction abnormal range after the derivative treatment; the target interaction abnormal range comprises a first interaction abnormal range and a derived constraint range; and calculating a first depolarization analysis result corresponding to the constraint range.
In an independent embodiment, the combining the depolarization analysis results of the first interaction anomaly range with the depolarization analysis results of the first interaction anomaly range to obtain a second interaction anomaly range after being spliced includes: dividing the target interaction abnormal range into a preset number of areas; calculating a corresponding second depolarization analysis result of each region; splicing the first depolarization analysis result with the second depolarization analysis result of each region to obtain a target depolarization analysis result after splicing each region; and setting the description contents of each area as corresponding target depolarization analysis results, obtaining a preset number of target areas after the description contents are set, and forming a second interaction abnormal range by the preset number of target areas.
In an embodiment of the independent implementation, the splicing the first depolarization analysis result with the second depolarization analysis result of each region to obtain a target depolarization analysis result after each region is spliced includes: performing first function processing on the first depolarization analysis result with a first trusted value to obtain a first target depolarization analysis result after the first function processing; performing second function processing on the second depolarization analysis result of each region by using a second credible value to obtain a second target depolarization analysis result after the second function processing of each region; and respectively splicing the first target depolarization analysis result and the second target depolarization analysis result of each region to obtain a target depolarization analysis result after splicing each region.
In an independent embodiment, the sum of the first trusted value and the second trusted value is one, and before the performing the first function on the first depolarization analysis result with the first trusted value to obtain the first target depolarization analysis result after the first function processing, the method further includes: receiving an input trusted value set by a user, and setting the input trusted value as a first trusted value; and calculating a corresponding second trusted value by combining the first trusted value.
In an independent embodiment, the loading the second interaction anomaly range into the user interaction information to obtain the evaluated target user interaction information includes: loading each target area to the user interaction information sequentially through a splicing method to obtain spliced transition user interaction information; and supplementing key information for the transition user interaction information to obtain the evaluated target user interaction information.
In an independent embodiment, the supplementing the key information for the transition user interaction information to obtain the estimated target user interaction information includes: cleaning the user interaction information to obtain cleaned user interaction information; determining corresponding key information based on the user interaction information and the user interaction information after the cleaning treatment; and supplementing the key information to the transition user interaction information to obtain the evaluated target user interaction information.
In an independent embodiment, the determining the first interaction anomaly range in the user interaction information includes: inputting the user interaction information into a configured preset classification thread, and outputting a first interaction abnormal range corresponding to the user interaction information; the configured preset classification thread is configured based on the user interaction information example and the corresponding interaction abnormal range identification.
In an independently implemented embodiment, the method further comprises: obtaining a user interaction information example and a corresponding interaction abnormal range identifier; inputting the user interaction information example to a preset classification thread, and outputting regression analysis possibility that each character in the user interaction information example belongs to an interaction abnormal range; determining a difference between the regression analysis probability and the interaction anomaly range identification; and carrying out iterative configuration on the preset classification threads based on the difference until the difference converges to obtain the configured preset classification threads.
In an independent embodiment, the loading the second interaction anomaly range into the user interaction information to obtain the evaluated target user interaction information includes: and loading the second interaction abnormal range to the user interaction information through a splicing method to obtain the evaluated target user interaction information.
In a second aspect, a big data based user information assessment system is provided, comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute the computer program to implement the method as described above.
According to the big data-based user information evaluation method and system, user interaction information to be evaluated is obtained, and a first interaction abnormal range in the user interaction information is determined; obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction anomaly range; splicing the depolarization analysis results of the first interaction abnormal range according to the first depolarization analysis results to obtain a spliced second interaction abnormal range; and loading the second interaction abnormal range to the user interaction information to obtain the evaluated target user interaction information. Therefore, the first interaction abnormal range is spliced by extracting the first depolarization analysis result of the constraint range surrounding the first interaction abnormal range, and the spliced second interaction abnormal range is loaded to the user interaction information, so that the user information can be accurately evaluated, key description content of the user interaction information can be effectively obtained, and better assistance is provided for subsequent services.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a user information evaluation method based on big data according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, a method for evaluating user information based on big data is shown, which may include the following steps 101-104.
In step 101, user interaction information to be evaluated is obtained, and a first interaction anomaly range in the user interaction information is determined.
The method and the device for evaluating the user interaction information acquire the user interaction information to be evaluated, wherein the user interaction information comprises a local interaction range.
In one possible implementation, the first interaction anomaly range may be marked by masking the corresponding local range, the first interaction anomaly range may be formed by a plurality of characters, and the determination of the first interaction anomaly range may be obtained by performing regression analysis on the annotated or configured preset classification threads.
The configuration process of the preset classification thread is as follows:
(1) Obtaining a user interaction information example and a corresponding interaction abnormal range identifier;
(2) Inputting the user interaction information example into a preset classification thread, and outputting regression analysis possibility that each character in the user interaction information example belongs to an interaction abnormal range;
(3) Determining a difference between the regression analysis probability and the interaction anomaly range identification;
(4) And carrying out iterative configuration on the preset classification thread based on the difference until the difference converges to obtain the configured preset classification thread.
The user interaction information examples refer to user interaction information containing interaction anomaly ranges, each user interaction information annotates accurate positions of the interaction anomaly ranges, the positions can be represented by a plurality of characters, the accurate positions are the interaction anomaly range identifications, and the preset number of the user interaction information examples can be a plurality of.
Thus, each user interaction information example can be input into the preset classification thread, the regression analysis possibility that each character in the user interaction information example belongs to the interaction anomaly range is output, the larger the regression analysis possibility is, the larger the possibility that the character is represented as the interaction anomaly range is, the smaller the regression analysis possibility is, the smaller the possibility that the character is represented as the interaction anomaly range is, and the regression analysis possibility is inaccurate because the preset classification thread is not configured.
Because the interaction anomaly range identifier clearly indicates the accurate possibility of whether each character in the user interaction information example is the interaction anomaly range, the interaction anomaly range identifier can be used as a learning target to determine the difference between the regression analysis possibility and the interaction anomaly range identifier, and the difference is used as a debugging standard to conduct guiding configuration on a preset classification thread.
Based on the above description, the determining the first interaction abnormal range in the user interaction information may be completed by inputting the user interaction information into the configured preset classification thread and outputting the first interaction abnormal range corresponding to the user interaction information.
The configured preset classification thread has the capability of accurately identifying the interaction abnormal range in the user interaction information through configuration, so that the accuracy of the first interaction abnormal range output by the preset classification thread is higher, and the model is automatically regressively analyzed, so that the labor cost is saved.
In step 102, a first depolarization analysis result corresponding to a constraint range surrounding a first interaction anomaly range is obtained.
The present embodiment may obtain a constraint range corresponding to the first interaction anomaly range, where the constraint range may be understood as a range of edge connection of the first interaction anomaly range, and the constraint range reflects real-time constraint descriptions about the first interaction anomaly range.
Further, a first depolarization analysis result of the constraint range may be calculated, where the first depolarization analysis result may be an average value of descriptions of the characters in the constraint range, specifically may be that the descriptions of the characters in the constraint range are summed, and the summed values are divided by a preset number of characters, so as to obtain the first depolarization analysis result as a real-time average description of the constraint range around the first interaction anomaly range.
In one embodiment, the obtaining the first depolarization analysis result corresponding to the constraint range surrounding the first interaction anomaly range includes:
(1) Performing derivative treatment on the first interaction abnormal range to obtain a target interaction abnormal range after the derivative treatment; wherein, the deriving process can be understood as amplifying the first interaction anomaly range; for example, a critical range is obtained in obtaining the first interaction abnormal range, and some relatively fine ranges are not extracted, so that the first interaction abnormal range needs to be expanded, so that the abnormal range can be obtained more accurately.
(2) And calculating a first depolarization analysis result corresponding to the constraint range.
In step 103, the depolarization analysis results of the first interaction anomaly range are spliced according to the first depolarization analysis results, so as to obtain a spliced second interaction anomaly range.
In order to solve the above-mentioned problem, the embodiment of the present application may splice a first depolarization analysis result representing real-time average description content of a constraint range around the first interaction anomaly range with a depolarization analysis result of the first interaction anomaly range, where the depolarization analysis result of the first interaction anomaly range may be calculated by counting a sum of description content values of characters in the first interaction anomaly range, dividing the sum of description content values by a preset number of characters in the first interaction anomaly range, and the depolarization analysis result reflects average description content in the first interaction anomaly range.
Therefore, a target average value of the first depolarization analysis result and the depolarization analysis result can be calculated, namely the first depolarization analysis result and the depolarization analysis result are summed, the summed value is divided by 2 to obtain the target average value, the target average value implies real-time average description content of a constraint range around a first interaction anomaly range, and average description content in the first interaction anomaly range is reserved, so that the description content values of all characters in the first interaction anomaly range can be set according to the target average value, a spliced second interaction anomaly range is obtained, the second interaction anomaly range is used for removing interaction anomalies in the first interaction anomaly range through splicing, description details in the first interaction anomaly range are reserved, and compared with a scheme of related technologies, the interaction anomaly evaluation is realized, and meanwhile the processing result is more accurate.
In one possible implementation embodiment, the stitching the descriptive content values of the first interaction anomaly range according to the first depolarization analysis result to obtain a stitched second interaction anomaly range includes:
(1) Dividing the target interaction abnormal range into a preset number of areas;
(2) Calculating a corresponding second depolarization analysis result of each region;
(3) Splicing the first depolarization analysis result with the second depolarization analysis result of each region to obtain a target depolarization analysis result after splicing each region;
(4) And setting the description contents of each area as corresponding target depolarization analysis results, obtaining a preset number of target areas after the description contents are set, and forming a second interaction abnormal range by the preset number of target areas.
Further, the target depolarization analysis results corresponding to the first depolarization analysis result and the second depolarization analysis result of each region can be calculated, namely, the first depolarization analysis result and the second depolarization analysis result of each region can be summed, and the summed value is divided by 2 to obtain the target depolarization analysis result of each region, wherein the target depolarization analysis result implies real-time average description content of a constraint range around the first interaction abnormal range, and the second depolarization analysis result in each region is reserved, so that the description content value of each region can be set as the corresponding target depolarization analysis result, a preset number of target regions after the description content is set is obtained, the preset number of target regions form a second interaction abnormal range, and as each target region in the second interaction abnormal range independently realizes the removal of interaction abnormal in the second interaction abnormal range, the description details in the target region are reserved, so that the processed data is more accurate.
In one possible implementation embodiment, the splicing the first depolarization analysis result with the second depolarization analysis result of each region to obtain the target depolarization analysis result after the splicing of each region includes:
(1.1) performing first function processing on the first depolarization analysis result with a first credible value to obtain a first target depolarization analysis result after the first function processing;
(1.2) performing second function processing on the second depolarization analysis result of each region by using a second credible value to obtain a second target depolarization analysis result after the second function processing of each region;
and (1.3) respectively splicing the first target depolarization analysis result and the second target depolarization analysis result of each region to obtain a target depolarization analysis result after splicing each region.
The first depolarization analysis result represents real-time average description content of a constraint range around the first interaction abnormal range, and the second depolarization analysis result of each region represents average description content in each region, so that the embodiment of the application can realize dynamic debugging of the splicing processing effect by setting a first trusted value and a second trusted value.
Further, the first function and the second function are set in advance.
Therefore, when the first depolarization analysis result and the second depolarization analysis result of each region are spliced, the weight of the first depolarization analysis result can be debugged through the first trusted value, and the weight of the second average value can be debugged through the second trusted value.
In step 104, the second interaction abnormal range is loaded to the user interaction information, and the estimated target user interaction information is obtained.
In one possible implementation embodiment, the loading the second interaction anomaly range into the user interaction information to obtain the evaluated target user interaction information includes: and loading the second interaction abnormal range to the user interaction information through a splicing method to obtain the evaluated target user interaction information.
In a possible implementation embodiment, the loading the second interaction anomaly range into the user interaction information to obtain the evaluated target user interaction information includes:
(1) Loading each target area to the user interaction information sequentially through a splicing method to obtain spliced transition user interaction information;
(2) And supplementing key information for the transition user interaction information to obtain the evaluated target user interaction information.
As can be seen from the foregoing, in the embodiments of the present application, the user interaction information to be evaluated is obtained, and the first interaction abnormal range in the user interaction information is determined; obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction anomaly range; splicing the depolarization analysis results of the first interaction abnormal range according to the first depolarization analysis results to obtain a spliced second interaction abnormal range; and loading the second interaction abnormal range to the user interaction information to obtain the evaluated target user interaction information. Therefore, the first interaction abnormal range is spliced by extracting the first depolarization analysis result of the constraint range surrounding the first interaction abnormal range, and the spliced second interaction abnormal range is loaded to the user interaction information, so that the user information can be accurately evaluated, key description content of the user interaction information can be effectively obtained, and better assistance is provided for subsequent services.
The methods described in connection with the above embodiments are described in further detail below by way of example.
In the present embodiment, description will be given taking an example in which the image processing apparatus is specifically integrated in a server, with specific reference to the following description.
The embodiment of the application provides another flow of the big data-based user information evaluation method. The method flow may include:
in step 201, the server obtains a user interaction information example and a corresponding interaction anomaly range identifier, inputs the user interaction information example into a preset classification thread, and outputs regression analysis possibility that each character in the user interaction information example belongs to the interaction anomaly range.
Thus, each user interaction information example can be input into the preset classification thread, and the regression analysis possibility that each character in the user interaction information example belongs to the french range is output, wherein the larger the regression analysis possibility is, the larger the possibility that the character is represented as the french range is, the smaller the regression analysis possibility is, and the smaller the possibility that the character is represented as the french range is.
In step 202, the server determines the difference between the regression analysis possibility and the interactive anomaly range identifier, and iteratively configures the preset classification thread based on the difference until the difference converges, thereby obtaining the configured preset classification thread.
In step 203, the server inputs the user interaction information into the configured preset classification thread, and outputs a first interaction abnormal range corresponding to the user interaction information.
The preset classification thread after configuration has the capability of accurately identifying the scope of the statue lines in the user interaction information through configuration, so that the user interaction information is input into the preset classification thread after configuration to output the corresponding first statue line scope of the user interaction information, the accuracy of the first statue line scope output by the preset classification thread is higher, and because the model is an autoregressive analysis, manual annotation is not needed, and the labor cost is saved.
In step 204, the server performs a derivatization process on the first interaction anomaly range to obtain a target interaction anomaly range after the derivatization process, and calculates a first depolarization analysis result corresponding to the constraint range.
In step 205, the server divides the target interaction anomaly range into a predetermined number of regions, and calculates a second depolarization analysis result corresponding to each region.
In step 206, the server receives the input trusted value set by the user and sets the input trusted value as a first trusted value, receives the input trusted value set by the user and sets the input trusted value as the first trusted value.
In step 207, the server performs a first function on the first depolarization analysis result with a first trusted value to obtain a first target depolarization analysis result after the first function is processed, performs a second function on the second depolarization analysis result of each region with a second trusted value to obtain a second target depolarization analysis result after the second function is processed, and performs stitching on the first target depolarization analysis result and the second target depolarization analysis result of each region to obtain a target depolarization analysis result after stitching of each region.
In step 208, the server sets the description content of each area as the corresponding target depolarization analysis result, obtains a preset number of target areas after the description content is set, and constructs the preset number of target areas into the second interaction anomaly range.
In step 209, the server loads each target area to the user interaction information sequentially through the splicing method, so as to obtain the spliced transition user interaction information.
In step 210, the server performs cleaning processing on the user interaction information to obtain user interaction information after cleaning processing, determines corresponding key information based on the user interaction information and the user interaction information after cleaning processing, supplements the key information to the transition user interaction information, and obtains the estimated target user interaction information.
On the basis of the above, there is provided a big data based user information evaluation apparatus comprising:
the abnormal range determining module is used for obtaining user interaction information to be evaluated and determining a first interaction abnormal range in the user interaction information;
the analysis result obtaining module is used for obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction abnormal range;
the abnormal range determining module is used for combining the first depolarization analysis result to splice the depolarization analysis result of the first interaction abnormal range to obtain a spliced second interaction abnormal range;
and the interaction information evaluation module is used for loading the second interaction abnormal range to the user interaction information to obtain the evaluated target user interaction information.
On the basis of the above, a big data based user information assessment system is shown comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and to execute it for carrying out the method as described above.
On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.
In summary, based on the above scheme, by obtaining user interaction information to be evaluated, and determining a first interaction abnormal range in the user interaction information; obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction anomaly range; splicing the depolarization analysis results of the first interaction abnormal range according to the first depolarization analysis results to obtain a spliced second interaction abnormal range; and loading the second interaction abnormal range to the user interaction information to obtain the evaluated target user interaction information. Therefore, the first interaction abnormal range is spliced by extracting the first depolarization analysis result of the constraint range surrounding the first interaction abnormal range, and the spliced second interaction abnormal range is loaded to the user interaction information, so that the user information can be accurately evaluated, key description content of the user interaction information can be effectively obtained, and better assistance is provided for subsequent services.
It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).
It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.
Claims (7)
1. A big data based user information assessment method, the method comprising:
obtaining user interaction information to be evaluated, and determining a first interaction abnormal range in the user interaction information;
obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction anomaly range;
splicing the depolarization analysis results of the first interaction abnormal range by combining the first depolarization analysis results to obtain a spliced second interaction abnormal range;
loading the second interaction abnormal range to the user interaction information to obtain evaluated target user interaction information;
wherein the obtaining a first depolarization analysis result corresponding to a constraint range surrounding the first interaction anomaly range includes:
performing derivative treatment on the first interaction abnormal range to obtain a target interaction abnormal range after the derivative treatment; the target interaction abnormal range comprises a first interaction abnormal range and a derived constraint range;
calculating a first depolarization analysis result corresponding to the constraint range;
the step of combining the first depolarization analysis result to splice the depolarization analysis result of the first interaction abnormal range to obtain a spliced second interaction abnormal range comprises the following steps:
dividing the target interaction abnormal range into a preset number of areas; calculating a corresponding second depolarization analysis result of each region;
splicing the first depolarization analysis result with the second depolarization analysis result of each region to obtain a target depolarization analysis result after splicing each region;
setting the description content of each area as a corresponding target depolarization analysis result, obtaining a preset number of target areas after the description content is set, and forming a second interaction abnormal range by the preset number of target areas;
wherein the determining the first interaction abnormal range in the user interaction information includes:
inputting the user interaction information into a configured preset classification thread, and outputting a first interaction abnormal range corresponding to the user interaction information; the configured preset classification thread is configured based on a user interaction information example and a corresponding interaction abnormal range identifier;
wherein the method further comprises:
obtaining a user interaction information example and a corresponding interaction abnormal range identifier; inputting the user interaction information example to a preset classification thread, and outputting regression analysis possibility that each character in the user interaction information example belongs to an interaction abnormal range;
determining a difference between the regression analysis probability and the interaction anomaly range identification;
performing iterative configuration on the preset classification threads based on the difference until the difference converges to obtain configured preset classification threads;
the first depolarization analysis result of the constraint range may be calculated, where the first depolarization analysis result may be an average value of descriptions of characters in the constraint range, specifically may be that the descriptions of the characters in the constraint range are summed, and the summed values are divided by a preset number of characters, so as to obtain the first depolarization analysis result as a real-time average description of the constraint range around the first interaction anomaly range.
2. The big data based user information evaluation method of claim 1, wherein the splicing the first depolarization analysis result with the second depolarization analysis result of each region to obtain the target depolarization analysis result after splicing each region includes:
performing first function processing on the first depolarization analysis result with a first trusted value to obtain a first target depolarization analysis result after the first function processing;
performing second function processing on the second depolarization analysis result of each region by using a second credible value to obtain a second target depolarization analysis result after the second function processing of each region;
and respectively splicing the first target depolarization analysis result and the second target depolarization analysis result of each region to obtain a target depolarization analysis result after splicing each region.
3. The big data based user information evaluation method of claim 2, wherein the sum of the first trusted value and the second trusted value is one, and the performing the first function on the first depolarization analysis result with the first trusted value, before obtaining the first target depolarization analysis result after the first function processing, further comprises: receiving an input trusted value set by a user, and setting the input trusted value as a first trusted value; and calculating a corresponding second trusted value by combining the first trusted value.
4. The big data based user information evaluation method according to claim 1, wherein the loading the second interaction anomaly range into the user interaction information to obtain the evaluated target user interaction information includes:
loading each target area to the user interaction information sequentially through a splicing method to obtain spliced transition user interaction information;
and supplementing key information for the transition user interaction information to obtain the evaluated target user interaction information.
5. The big data based user information evaluation method according to claim 4, wherein the supplementing key information for the transition user interaction information to obtain the evaluated target user interaction information includes:
cleaning the user interaction information to obtain cleaned user interaction information;
determining corresponding key information based on the user interaction information and the user interaction information after the cleaning treatment;
and supplementing the key information to the transition user interaction information to obtain the evaluated target user interaction information.
6. The big data based user information evaluation method according to claim 1, wherein the loading the second interaction anomaly range into the user interaction information to obtain the evaluated target user interaction information includes: and loading the second interaction abnormal range to the user interaction information through a splicing method to obtain the evaluated target user interaction information.
7. A big data based user information assessment system, characterized by comprising a processor and a memory in communication with each other, the processor being arranged to read a computer program from the memory and to execute it for implementing the method according to any of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311672376.2A CN117370767B (en) | 2023-12-07 | 2023-12-07 | User information evaluation method and system based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311672376.2A CN117370767B (en) | 2023-12-07 | 2023-12-07 | User information evaluation method and system based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117370767A CN117370767A (en) | 2024-01-09 |
CN117370767B true CN117370767B (en) | 2024-02-27 |
Family
ID=89406274
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311672376.2A Active CN117370767B (en) | 2023-12-07 | 2023-12-07 | User information evaluation method and system based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117370767B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117809849B (en) * | 2024-02-29 | 2024-05-03 | 四川赛尔斯科技有限公司 | Analysis method and system for walking postures of old people with cognitive dysfunction |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109524085A (en) * | 2018-10-25 | 2019-03-26 | 广州市和声信息技术有限公司 | It is a kind of based on interactive cognitive analysis method and system |
CN110491490A (en) * | 2019-07-11 | 2019-11-22 | 深圳市翩翩科技有限公司 | A kind of doctor's appraisal procedure and device |
CN113378554A (en) * | 2021-06-08 | 2021-09-10 | 湖南创星科技股份有限公司 | Medical information intelligent interaction method and system |
WO2022213816A1 (en) * | 2021-04-06 | 2022-10-13 | 华为云计算技术有限公司 | Data analysis method, data analysis system, computing device, storage medium, and program product |
CN115757370A (en) * | 2022-10-20 | 2023-03-07 | 郜布轩 | User information communication method and system based on Internet of things |
CN116506206A (en) * | 2023-05-15 | 2023-07-28 | 东南大学 | Big data behavior analysis method and system based on zero trust network user |
CN116720119A (en) * | 2023-06-25 | 2023-09-08 | 滨州诺防跟网络科技有限公司 | Big data identification method and system applied to multi-terminal service interaction |
CN117037982A (en) * | 2023-03-24 | 2023-11-10 | 九为(浙江)网络科技有限公司 | Medical big data information intelligent acquisition method and system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11042784B2 (en) * | 2017-09-15 | 2021-06-22 | M37 Inc. | Machine learning system and method for determining or inferring user action and intent based on screen image analysis |
US11847169B2 (en) * | 2020-12-18 | 2023-12-19 | Shanghai Henghui Intellectual Property Service Co., Ltd. | Method for data processing and interactive information exchange with feature data extraction and bidirectional value evaluation for technology transfer and computer used therein |
US20220215948A1 (en) * | 2021-01-07 | 2022-07-07 | Abiomed, Inc. | Network-based medical apparatus control and data management systems |
-
2023
- 2023-12-07 CN CN202311672376.2A patent/CN117370767B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109524085A (en) * | 2018-10-25 | 2019-03-26 | 广州市和声信息技术有限公司 | It is a kind of based on interactive cognitive analysis method and system |
CN110491490A (en) * | 2019-07-11 | 2019-11-22 | 深圳市翩翩科技有限公司 | A kind of doctor's appraisal procedure and device |
WO2022213816A1 (en) * | 2021-04-06 | 2022-10-13 | 华为云计算技术有限公司 | Data analysis method, data analysis system, computing device, storage medium, and program product |
CN113378554A (en) * | 2021-06-08 | 2021-09-10 | 湖南创星科技股份有限公司 | Medical information intelligent interaction method and system |
CN115757370A (en) * | 2022-10-20 | 2023-03-07 | 郜布轩 | User information communication method and system based on Internet of things |
CN117037982A (en) * | 2023-03-24 | 2023-11-10 | 九为(浙江)网络科技有限公司 | Medical big data information intelligent acquisition method and system |
CN116506206A (en) * | 2023-05-15 | 2023-07-28 | 东南大学 | Big data behavior analysis method and system based on zero trust network user |
CN116720119A (en) * | 2023-06-25 | 2023-09-08 | 滨州诺防跟网络科技有限公司 | Big data identification method and system applied to multi-terminal service interaction |
Non-Patent Citations (4)
Title |
---|
An Autocorrelation-based LSTM-Autoencoder for Anomaly Detection on Time-Series Data;Hajar Homayouni等;《2020 IEEE International Conference on Big Data (Big Data)》;5068-5077 * |
Modeling and Assessing User Interaction in Big Data Visualization Systems;Dario Benvenuti等;《Human-Computer Interaction – INTERACT 2023》;86-109 * |
基于Xen的异常行为在线检测平台研究与设计;牛鹏飞等;《中国计算机学会.第31次全国计算机安全学术交流会论文集》;6 * |
基于大数据的计算机网络信息安全防护与信息评估算法研究;刘浚哲等;《网络安全和信息化》(第8期);136-138 * |
Also Published As
Publication number | Publication date |
---|---|
CN117370767A (en) | 2024-01-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11835987B2 (en) | Methods and apparatus for finding long methods in code | |
CN117370767B (en) | User information evaluation method and system based on big data | |
CN109815147B (en) | Test case generation method, device, server and medium | |
KR101979329B1 (en) | Method and apparatus for tracking security vulnerable input data of executable binaries thereof | |
CN110688111A (en) | Configuration method, device, server and storage medium of business process | |
US20210405980A1 (en) | Long method autofix engine | |
CN112882933A (en) | Script recording method, device, equipment and storage medium | |
CN112131573A (en) | Method and device for detecting security vulnerability and storage medium | |
CN109388568B (en) | Code testing method and device | |
US10628140B2 (en) | Program code generation apparatus | |
CN113505895A (en) | Machine learning engine service system, model training method and configuration method | |
US11068463B2 (en) | System and method for managing log data | |
CN116204681A (en) | Short video release information detection method, system and cloud platform | |
US20230107164A1 (en) | System and method for vulnerability detection in computer code | |
CN113284141A (en) | Model determination method, device and equipment for defect detection | |
US20130080137A1 (en) | Conversion method and system | |
CN109885491B (en) | Method for detecting existence of data overflow expression and terminal equipment | |
WO2022222499A1 (en) | Code processing method, and system, cluster, medium and program product | |
CN117520201A (en) | Reverse ambiguity test method and device, electronic equipment and storage medium | |
CN115982013A (en) | Method and device for visualizing automatic case flow, computer equipment and storage medium | |
CN113190453A (en) | User interface testing method, device, server and medium | |
CN116048995A (en) | Method, system, medium, equipment and terminal for configuring abnormal information | |
CN117435464A (en) | Software testing method and device, electronic equipment and computer readable storage medium | |
CN117370181A (en) | Code optimization method and device, terminal equipment and computer readable storage medium | |
JP2013061893A (en) | Information processor, information processing method, and program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |